Matrix BOB
A Matrix bot to experiment with autoregressive LLMs.
Bob integrates with any OpenAI-compatible API (e.g. Ollama, LiteLLM) and can:
- carry on conversations in Matrix rooms
- transcribe audio messages and use them as input
- describe and process images
- scrape the web and summarize content
Install
python -m venv .venv
source .venv/bin/activate
pip install .
Development
pip install --editable .
Configuration
Copy the sample config and fill in your values:
cp config/sample.config.yaml config/config.yaml
Minimum fields to set: Matrix credentials (user_id, user_password, homeserver_url, device_id),
inviters, power_users, and the openai.url pointing at your LLM backend.
Run
Bob requires a PostgreSQL database. The docker/ directory contains a docker-compose.yaml
that starts the database and the bot together:
cd docker
docker compose up -d
Or run locally after starting PostgreSQL separately:
bob [config/config.yaml]
Config file defaults to config/config.yaml.
Database migrations
alembic upgrade head
Run this once on first setup and after any update that includes new migrations.
Deployment
See docs/deployment.md for a full production deployment guide (Docker Compose + systemd + GitHub Actions CI).
Open source and contributing
Contributions are welcome — please open an issue or discussion before starting significant work. See CONTRIBUTING.md for guidelines.
Thanks to
Metadata
Release files for pawnai-matrix 0.3.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| pawnai_matrix-0.3.0.tar.gz | 185.3 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| pawnai_matrix-0.3.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 274.3 kB
Release files / pawnai_matrix-0.3.0.tar.gz
| Download URL | pawnai_matrix-0.3.0.tar.gz |
|---|---|
| Size | 185.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
1801be30ce703878ebd6c1e5cadc8176103f41df707f5e220bed3e0788c78726
|
|
BLAKE2b-256 checksum How to use checksums |
46ea374f859f8c3a575c53e178c9a0b111918b2fbc1e8ad018198737d4899986
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Apr 12, 2026.
Transparency logRelease files / pawnai_matrix-0.3.0-py3-none-any.whl
| Download URL | pawnai_matrix-0.3.0-py3-none-any.whl |
|---|---|
| Size | 89.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
7c4f2cc086f9e05d444a19244b2b9ab5d44e48db9d0e57cfec4371b855e0ac66
|
|
BLAKE2b-256 checksum How to use checksums |
a7a1058abedbf1bebeb2815a86b86be41bd4f20b9e90456c3d4d061ada21c599
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Apr 12, 2026.
Transparency log